vue enhance

utils/audit/audit_doc.py

@@ -4,14 +4,14 @@ import tiktoken
 import textstat
 from docx import Document
 import io
-from rake_nltk import Rake
-import nltk
-from nltk.corpus import stopwords
+# from rake_nltk import Rake
+# import nltk
+# from nltk.corpus import stopwords
 from openai import OpenAI
 
 # Download NLTK stopwords
-nltk.download('stopwords')
-nltk.download('punkt')
+# nltk.download('stopwords')
+# nltk.download('punkt')
 
 #function to use gpt4o-mini
 def extract_relevant_keywords(prompt: str) -> str:
@@ -65,10 +65,10 @@ def evaluate_text_quality(text: str) -> dict:
     # Scale the global score to 0-5
     global_score_0_5 = global_score * 5
 
-def extract_keywords(text):
-    rake = Rake(stopwords.words('french'))
-    rake.extract_keywords_from_text(text)
-    return rake.get_ranked_phrases()
+# def extract_keywords(text):
+#     rake = Rake(stopwords.words('french'))
+#     rake.extract_keywords_from_text(text)
+#     return rake.get_ranked_phrases()
 
 
 
@@ -168,8 +168,8 @@ def audit_descriptif_pdf(file,max_img_width) -> dict:
     
     # Extract key words from the document
     text = " ".join([page["texte"] for page in doc_content.values()])
-    key_words = extract_keywords(text)
-    list_key_words_text = "\n".join(key_words[:10])
+    # key_words = extract_keywords(text)
+    # list_key_words_text = "\n".join(key_words[:10])
     prompt = f'''Voici le document:
         - {text}
         Veuillez extraire les cinq mots clés les plus pertinents de cette liste. Chaque mot clé doit contenir au maximum deux mots.